INDEX

Explanations

code structures indicating class definitions and object-oriented features

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RegressionTest

-0.59

 phép

-0.50

المشاركات

-0.50

 Shoulders

-0.48

Revenir

-0.47

Raid

-0.47

Mover

-0.46

newArrayList

-0.45

 weighing

-0.45

lawesi

-0.45

POSITIVE LOGITS

 nothing

0.82

nothing

0.79

Nothing

0.75

 Nothing

0.74

 nothin

0.73

 NOTHING

0.71

}}

0.67

}})

0.66

}}

0.66

 anything

0.66

Activations Density 0.068%

code structures indicating class definitions and object-oriented features

No Comments

No Known Activations